design-first-ui-prompting
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of Markdown and configuration metadata that define prompting workflows. No executable scripts (.sh, .py, .js) or binary files are included.- [PROMPT_INJECTION]: Analysis of the prompting templates and instructions shows no evidence of jailbreak attempts, safety filter bypasses, or instructions intended to override core agent behavior. The skill focuses on improving the quality of UI generation outputs.- [DATA_EXFILTRATION]: There are no hardcoded secrets, API keys, or commands that access sensitive system files (e.g., .ssh, .aws). The mention of a local 'refs/' directory is for user-managed design inspiration files.- [EXTERNAL_DOWNLOADS]: All external links and service mentions point to established and well-known design industry resources, such as Figma and Mobbin. No automated downloads of untrusted code or scripts are present.
Audit Metadata